Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3425 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3844. Min Range: -8.3844
Max Act: 8.3844. Min Act: -0.1700
Data Index: 5146780 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3844. Min Range: -8.3844
Max Act: 8.0094. Min Act: -0.1700
Data Index: 8262978 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3844. Min Range: -8.3844
Max Act: 7.9469. Min Act: -0.1700
Data Index: 3205411 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3844. Min Range: -8.3844
Max Act: 7.8844. Min Act: -0.1700
Data Index: 7768394 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3844. Min Range: -8.3844
Max Act: 7.8844. Min Act: -0.1700
Data Index: 645132 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3844. Min Range: -8.3844
Max Act: 7.8219. Min Act: -0.1700
Data Index: 3896503 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3844. Min Range: -8.3844
Max Act: 7.6969. Min Act: -0.1700
Data Index: 2408320 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3844. Min Range: -8.3844
Max Act: 7.6969. Min Act: -0.1700
Data Index: 1488242 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3844. Min Range: -8.3844
Max Act: 7.6969. Min Act: -0.1700
Data Index: 7317029 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3844. Min Range: -8.3844
Max Act: 7.6344. Min Act: -0.1700
Data Index: 681345 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3844. Min Range: -8.3844
Max Act: 7.5719. Min Act: -0.1700
Data Index: 3499368 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3844. Min Range: -8.3844
Max Act: 7.6344. Min Act: -0.1700
Data Index: 3219601 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3844. Min Range: -8.3844
Max Act: 7.6969. Min Act: -0.1700
Data Index: 3677235 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3844. Min Range: -8.3844
Max Act: 7.6344. Min Act: -0.1700
Data Index: 4310786 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3844. Min Range: -8.3844
Max Act: 7.5719. Min Act: -0.1700
Data Index: 4320060 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3844. Min Range: -8.3844
Max Act: 7.5719. Min Act: -0.1700
Data Index: 6284501 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3844. Min Range: -8.3844
Max Act: 7.5094. Min Act: -0.1700
Data Index: 3105198 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3844. Min Range: -8.3844
Max Act: 7.5094. Min Act: -0.1700
Data Index: 4478516 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3844. Min Range: -8.3844
Max Act: 7.5094. Min Act: -0.1700
Data Index: 1813218 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3844. Min Range: -8.3844
Max Act: 7.4782. Min Act: -0.1700
Data Index: 377077 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19